New shader translator implementation (#654)

* Start implementing a new shader translator * Fix shift instructions and a typo * Small refactoring on StructuredProgram, move RemovePhis method to a separate class * Initial geometry shader support * Implement TLD4 * Fix -- There's no negation on FMUL32I * Add constant folding and algebraic simplification optimizations, nits * Some leftovers from constant folding * Avoid cast for constant assignments * Add a branch elimination pass, and misc small fixes * Remove redundant branches, add expression propagation and other improvements on the code * Small leftovers -- add missing break and continue, remove unused properties, other improvements * Add null check to handle empty block cases on block visitor * Add HADD2 and HMUL2 half float shader instructions * Optimize pack/unpack sequences, some fixes related to half float instructions * Add TXQ, TLD, TLDS and TLD4S shader texture instructions, and some support for bindless textures, some refactoring on codegen * Fix copy paste mistake that caused RZ to be ignored on the AST instruction * Add workaround for conditional exit, and fix half float instruction with constant buffer * Add missing 0.0 source for TLDS.LZ variants * Simplify the switch for TLDS.LZ * Texture instructions related fixes * Implement the HFMA instruction, and some misc. fixes * Enable constant folding on UnpackHalf2x16 instructions * Refactor HFMA to use OpCode* for opcode decoding rather than on the helper methods * Remove the old shader translator * Remove ShaderDeclInfo and other unused things * Add dual vertex shader support * Add ShaderConfig, used to pass shader type and maximum cbuffer size * Move and rename some instruction enums * Move texture instructions into a separate file * Move operand GetExpression and locals management to OperandManager * Optimize opcode decoding using a simple list and binary search * Add missing condition for do-while on goto elimination * Misc. fixes on texture instructions * Simplify TLDS switch * Address PR feedback, and a nit
2019-04-17 20:57:08 -03:00 · 2019-04-17 20:57:08 -03:00 · 6b23a2c125
commit 6b23a2c125
parent b2e88b04a8
207 changed files with 11514 additions and 6311 deletions
--- a/Ryujinx.Graphics/Shader/IntermediateRepresentation/Instruction.cs
+++ b/Ryujinx.Graphics/Shader/IntermediateRepresentation/Instruction.cs
@ -0,0 +1,87 @@
+using System;
+
+namespace Ryujinx.Graphics.Shader.IntermediateRepresentation
+{
+    [Flags]
+    enum Instruction
+    {
+        Absolute = 1,
+        Add,
+        BitfieldExtractS32,
+        BitfieldExtractU32,
+        BitfieldInsert,
+        BitfieldReverse,
+        BitwiseAnd,
+        BitwiseExclusiveOr,
+        BitwiseNot,
+        BitwiseOr,
+        Branch,
+        BranchIfFalse,
+        BranchIfTrue,
+        Ceiling,
+        Clamp,
+        ClampU32,
+        CompareEqual,
+        CompareGreater,
+        CompareGreaterOrEqual,
+        CompareGreaterOrEqualU32,
+        CompareGreaterU32,
+        CompareLess,
+        CompareLessOrEqual,
+        CompareLessOrEqualU32,
+        CompareLessU32,
+        CompareNotEqual,
+        ConditionalSelect,
+        ConvertFPToS32,
+        ConvertS32ToFP,
+        ConvertU32ToFP,
+        Copy,
+        Cosine,
+        Discard,
+        Divide,
+        EmitVertex,
+        EndPrimitive,
+        ExponentB2,
+        Floor,
+        FusedMultiplyAdd,
+        IsNan,
+        LoadConstant,
+        LoadGlobal,
+        LoadLocal,
+        LogarithmB2,
+        LogicalAnd,
+        LogicalExclusiveOr,
+        LogicalNot,
+        LogicalOr,
+        LoopBreak,
+        LoopContinue,
+        MarkLabel,
+        Maximum,
+        MaximumU32,
+        Minimum,
+        MinimumU32,
+        Multiply,
+        Negate,
+        PackDouble2x32,
+        PackHalf2x16,
+        ReciprocalSquareRoot,
+        Return,
+        ShiftLeft,
+        ShiftRightS32,
+        ShiftRightU32,
+        Sine,
+        SquareRoot,
+        StoreGlobal,
+        StoreLocal,
+        Subtract,
+        TextureSample,
+        TextureSize,
+        Truncate,
+        UnpackDouble2x32,
+        UnpackHalf2x16,
+
+        Count,
+        FP   = 1 << 16,
+        Mask = 0xffff
+    }
+}